Abstract
Attribute reduction, also known as feature selection, is a common problem by selecting a subset of relevant attributes (e.g. features) to reach efficient learning/mining. Many attribute reduction methods have been proposed however, quite often, these methods are still computationally time-consuming while handling large-scale data. To overcome this shortcoming, we present a novel accelerator based on the positive region, by deleting the learned/discernible instance pairs in the process of attribute reduction, which can avoid redundant computation and accelerate attribute reduction. Our experiments numerically demonstrate that the proposed accelerator can reach drastically faster computation than previous methods, especially on the datasets with a large number of instances.
| Original language | English |
|---|---|
| Pages (from-to) | 533-550 |
| Number of pages | 18 |
| Journal | Information Sciences |
| Volume | 503 |
| Early online date | 10 Jul 2019 |
| DOIs | |
| Publication status | Published - Nov 2019 |
| Externally published | Yes |
Bibliographical note
This work is supported by National Key Research & Develop Program of China (2017YFB1400700), National Key Research & Develop Plan (2018YFB1004401, 2016YFB1000702), NSFC under the grant No. 61732006, 61532021, 61772536, 61772537, 61702522 and NSSFC (No.12\&ZD220), National Basic Research Program of China (973) (No. 2014CB340402), National High Technology Research and Development Program of China (863) (No. 2014AA015204) and the Fundamental Research Funds for the Central Universities, and the Research Funds of Renmin University of China (15XNLQ06). It was partially done when the authors worked in SA Center for Big Data Research in RUC. This Center is funded by a Chinese National 111 Project Attracting.Keywords
- Accelerator
- Attribute reduction
- Fuzzy rough techniques
- Positive region